voicebox Docker & Self-Hosted Deployment

---
# ROCm (AMD GPU) overlay for Voicebox
#
#   docker compose -f docker-compose.yml -f docker-compose.rocm.yml up --build
#
# Requires ROCm drivers on the host:
# https://rocm.docs.amd.com/projects/install-on-linux
# RDNA4 (RX 9000): export ROCM_VERSION=7.2 (default 6.3 covers RDNA1-3).

services:
  voicebox:
    build:
      context: .
      args:
        PYTORCH_VARIANT: rocm
        ROCM_VERSION: ${ROCM_VERSION:-6.3}

    devices:
      - /dev/kfd
      - /dev/dri

    environment:
      # HSA_OVERRIDE_GFX_VERSION forces the ROCm runtime to treat the GPU as a
      # specific GFX version when auto-detection fails or the GPU is newer than
      # the ROCm release. app.py sets 10.3.0 (RDNA2) by default; override here
      # for your GPU family:
      #   RDNA4 / RX 9000 series:              12.0.0
      #                                           (requires ROCM_VERSION=7.2)
      #   RDNA3 / RX 7000 series / Strix Halo: 11.0.0
      #   RDNA2 / RX 6000 series:              10.3.0
      #   RDNA1 / RX 5000 series:              10.1.0
      #   Vega / GCN5:                          9.0.0
      - HSA_OVERRIDE_GFX_VERSION=${HSA_OVERRIDE_GFX_VERSION:-}

      # Tune the ROCm memory allocator
      - PYTORCH_HIP_ALLOC_CONF=garbage_collection_threshold:0.8,max_split_size_mb:512

      # Redirect MIOpen kernel cache to a writable, persistent directory.
      # Without this, MIOpen may fail to write its cache and throw
      # miopenStatusUnknownError on fresh containers.
      - MIOPEN_USER_DB_PATH=/app/data/cache/miopen_db
      - MIOPEN_CUSTOM_CACHE_DIR=/app/data/cache/miopen_cache

      # Use fast heuristics for kernel selection instead of exhaustive
      # benchmarking. On RDNA4, exhaustive mode tries kernels that fail to
      # allocate workspace memory (ptr: 0 size: 0), causing system stuttering
      # on every generation even when the cache is present.
      - MIOPEN_FIND_MODE=FAST